© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12624
    Prev
    Next
    INDEX
    Explanations

    C code related to the "mantis" device driver, particularly its PCI configuration and I2C communication functions

    oai_token-act-pair · gemini-2.0-flash

    pci

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reverse
    -0.50
    ervor
    -0.46
    otras
    -0.45
    ictus
    -0.45
     response
    -0.44
     sign
    -0.44
     Reverse
    -0.43
    setcounter
    -0.43
    intellij
    -0.42
     lạc
    -0.42
    POSITIVE LOGITS
    +:+
    0.79
     pinulongan
    0.79
    principalTable
    0.78
    OGND
    0.71
     MainAxisSize
    0.66
    RenderAtEndOf
    0.66
     onCancelled
    0.65
     يتيمه
    0.63
    ⓧ
    0.63
     ویکی‌پدی
    0.63
    Activations Density 2.973%

    No Known Activations